Prediction of Pt, Ir, Ru, and Rh complexes light absorption in the therapeutic window for phototherapy using machine learning

Barretta P., Scoditti S., Belletto D., Ponte F., Vigna V., Mazzone G., Sicilia E.

AbstractThe outcomes of DFT‐based calculations are here reported to assess the applicability of two synthesized polypyridyl Ru(II) complexes, bearing ethynyl nile red (NR) on a bpy ligand, and two analogues, bearing modified‐NR, in photodynamic therapy. The absorption spectra, together with the non‐radiative rate constants for the S1 – Tn intersystem crossing transitions, have been computed for this purpose. Calculations evidence that the structural modification on the chromophore destabilizes the HOMO of the complexes thus reducing the H‐L gap and, consequently, red shifting the maximum absorption wavelength within the therapeutic window, up to 620 nm. Moreover, the favored ISC process from the bright state involves the triplet state closest in energy, which is also characterized by the highest SOC value and by the involvement of the whole bpy ligand bearing the chromophore in delocalising the unpaired electrons. These outcomes show that the photophysical behavior of the complexes is dominated by the chromophore.

Vigna V., Cova T.F., Nunes S.C., Pais A.A., Sicilia E.

Siegel R.L., Giaquinto A.N., Jemal A.

AbstractEach year, the American Cancer Society estimates the numbers of new cancer cases and deaths in the United States and compiles the most recent data on population‐based cancer occurrence and outcomes using incidence data collected by central cancer registries (through 2020) and mortality data collected by the National Center for Health Statistics (through 2021). In 2024, 2,001,140 new cancer cases and 611,720 cancer deaths are projected to occur in the United States. Cancer mortality continued to decline through 2021, averting over 4 million deaths since 1991 because of reductions in smoking, earlier detection for some cancers, and improved treatment options in both the adjuvant and metastatic settings. However, these gains are threatened by increasing incidence for 6 of the top 10 cancers. Incidence rates increased during 2015–2019 by 0.6%–1% annually for breast, pancreas, and uterine corpus cancers and by 2%–3% annually for prostate, liver (female), kidney, and human papillomavirus‐associated oral cancers and for melanoma. Incidence rates also increased by 1%–2% annually for cervical (ages 30–44 years) and colorectal cancers (ages <55 years) in young adults. Colorectal cancer was the fourth‐leading cause of cancer death in both men and women younger than 50 years in the late‐1990s but is now first in men and second in women. Progress is also hampered by wide persistent cancer disparities; compared to White people, mortality rates are two‐fold higher for prostate, stomach and uterine corpus cancers in Black people and for liver, stomach, and kidney cancers in Native American people. Continued national progress will require increased investment in cancer prevention and access to equitable treatment, especially among American Indian and Alaska Native and Black individuals.

Eslami M., Memarsadeghi O., Davarpanah A., Arti A., Nayernia K., Behnam B.

The management of metastatic cancer is complicated by chemotherapy resistance. This manuscript provides a comprehensive academic review of strategies to overcome chemotherapy resistance in metastatic cancer. The manuscript presents background information on chemotherapy resistance in metastatic cancer cells, highlighting its clinical significance and the current challenges associated with using chemotherapy to treat metastatic cancer. The manuscript delves into the molecular mechanisms underlying chemotherapy resistance in subsequent sections. It discusses the genetic alterations, mutations, and epigenetic modifications that contribute to the development of resistance. Additionally, the role of altered drug metabolism and efflux mechanisms, as well as the activation of survival pathways and evasion of cell death, are explored in detail. The strategies to overcome chemotherapy resistance are thoroughly examined, covering various approaches that have shown promise. These include combination therapy approaches, targeted therapies, immunotherapeutic strategies, and the repurposing of existing drugs. Each strategy is discussed in terms of its rationale and potential effectiveness. Strategies for early detection and monitoring of chemotherapy drug resistance, rational drug design vis-a-vis personalized medicine approaches, the role of predictive biomarkers in guiding treatment decisions, and the importance of lifestyle modifications and supportive therapies in improving treatment outcomes are discussed. Lastly, the manuscript outlines the clinical implications of the discussed strategies. It provides insights into ongoing clinical trials and emerging therapies that address chemotherapy resistance in metastatic cancer cells. The manuscript also explores the challenges and opportunities in translating laboratory findings into clinical practice and identifies potential future directions and novel therapeutic avenues. This comprehensive review provides a detailed analysis of strategies to overcome chemotherapy resistance in metastatic cancer. It emphasizes the importance of understanding the molecular mechanisms underlying resistance and presents a range of approaches for addressing this critical issue in treating metastatic cancer.

Barretta P., Mazzone G.

The mechanism of action by computational exploration of an Ir(iii) complex bearing an aryl boronic acid moiety aiming at detecting H2O2 in cancer cells to generate an Ir(iii)-based phototosensitizer and quinone methide able to scavenge GSH.

McNaughton A.D., Joshi R.P., Knutson C.R., Fnu A., Luebke K.J., Malerich J.P., Madrid P.B., Kumar N.

Kaneko H.

Shao J., Liu Y., Yan J., Yan Z., Wu Y., Ru Z., Liao J., Miao X., Qian L.

Fluorescent molecules are important tools in biological detection, and numerous efforts have been made to develop compounds to meet the desired photophysical properties. For example, tuning the wavelength allows an appropriate penetration depth with minimal interference from the autofluorescence/scattering for a better signal-to-noise contrast. However, there are limited guidelines to rationally design or computationally predict the optical properties from first principles, and factors like the solvent effects will make it more complicated. Herein, we established a database (SMFluo1) of 1181 solvated small-molecule fluorophores covering the ultraviolet-visible-near-infrared absorption window and developed new machine learning models based on deep neural networks for accurately predicting photophysical parameters. The optimal system was applied to 120 out-of-sample compounds, and it exhibited remarkable accuracy with a mean relative error of 1.52%. In this new paradigm, a deep learning algorithm is promising to complement conventional theoretical and experimental studies of fluorophores and to greatly accelerate the discovery of new dyes. Due to its simplicity and efficiency, data from newly developed fluorophores can be easily supplemented to this system to further improve the accuracy across various dye families.

Ksenofontov A.A., Lukanov M.M., Bocharov P.S., Berezin M.B., Tetko I.V.

A possibility to accurately predict the absorption maximum wavelength of BODIPYs was investigated. We found that previously reported models had a low accuracy (40-57 nm) to predict BODIPYs due to the limited dataset sizes and/or number of BODIPYs (few hundreds). New models developed in this study were based on data of 6000-plus fluorescent dyes (including 4000-plus BODIPYs) and the deep neural network architecture. The high prediction accuracy (five-fold cross-validation room mean squared error (RMSE) of 18.4 nm) was obtained using a consensus model, which was more accurate than individual models. This model provided the excellent accuracy (RMSE of 8 nm) for molecules previously synthesized in our laboratory as well as for prospective validation of three new BODIPYs. We found that solvent properties did not significantly influence the model accuracy since only few BODIPYs exhibited solvatochromism. The analysis of large prediction errors suggested that compounds able to have intermolecular interactions with solvent or salts were likely to be incorrectly predicted. The consensus model is freely available at https://ochem.eu/article/134921 and can help the other researchers to accelerate design of new dyes with desired properties.

Rusanov A.I., Dmitrieva O.A., Mamardashvili N.Z., Tetko I.V.

The development of new functional materials based on porphyrins requires fast and accurate prediction of their spectral properties. The available models in the literature for absorption wavelength and extinction coefficient of the Soret band have low accuracy for this class of compounds. We collected spectral data for porphyrins to extend the literature set and compared the performance of global and local models for their modelling using different machine learning methods. Interestingly, extension of the public database contributed models with lower accuracies compared to the models, which we built using porphyrins only. The later model calculated acceptable RMSE = 2.61 for prediction of the absorption band of 335 porphyrins synthesized in our laboratory, but had a low accuracy (RMSE = 0.52) for extinction coefficient. A development of models using only compounds from our laboratory significantly decreased errors for these compounds (RMSE = 0.5 and 0.042 for absorption band and extinction coefficient, respectively), but limited their applicability only to these homologous series. When developing models, one should clearly keep in mind their potential use and select a strategy that could contribute the most accurate predictions for the target application. The models and data are publicly available.

Mamede R., Pereira F., Aires-de-Sousa J.

Machine learning (ML) algorithms were explored for the classification of the UV–Vis absorption spectrum of organic molecules based on molecular descriptors and fingerprints generated from 2D chemical structures. Training and test data (~ 75 k molecules and associated UV–Vis data) were assembled from a database with lists of experimental absorption maxima. They were labeled with positive class (related to photoreactive potential) if an absorption maximum is reported in the range between 290 and 700 nm (UV/Vis) with molar extinction coefficient (MEC) above 1000 Lmol−1 cm−1, and as negative if no such a peak is in the list. Random forests were selected among several algorithms. The models were validated with two external test sets comprising 998 organic molecules, obtaining a global accuracy up to 0.89, sensitivity of 0.90 and specificity of 0.88. The ML output (UV–Vis spectrum class) was explored as a predictor of the 3T3 NRU phototoxicity in vitro assay for a set of 43 molecules. Comparable results were observed with the classification directly based on experimental UV–Vis data in the same format.

Anas A., Sobhanan J., Sulfiya K.M., Jasmin C., Sreelakshmi P.K., Biju V.

• Photodynamic therapy of microbial infections. • Photosensitization and reactive oxygen species generation. • Visible and NIR light sources for photodynamic therapy. • Recent clinical progresses of PACT. Photodynamic therapy (PDT) and photodynamic antimicrobial chemotherapy (PACT) combine light and photosensitizers to treat cancers and microbial infections, respectively. In PACT, the excitation of a photosensitizer drug with appropriate light generates reactive oxygen species (ROS) that kill pathogens in the proximity of the drug. PACT has considerably advanced with new light sources, biocompatible photosensitizers, bioconjugate methods, and efficient ROS production. The PACT technology has evolved to compete with or replace antibiotics, reducing the burden of antibiotic resistance. This review updates recent advances in PACT, with special references to light sources, photosensitizers, and emerging applications to microbial infestations. We also discuss PACT applied to COVID-19 causing SARS-CoV-2 treatment and disinfecting food materials and water. Finally, we discuss the pathogen selectivity and efficiency of PACT.

Cha G., Moon H., Kim Y.

Construction and demolition waste (DW) generation information has been recognized as a tool for providing useful information for waste management. Recently, numerous researchers have actively utilized artificial intelligence technology to establish accurate waste generation information. This study investigated the development of machine learning predictive models that can achieve predictive performance on small datasets composed of categorical variables. To this end, the random forest (RF) and gradient boosting machine (GBM) algorithms were adopted. To develop the models, 690 building datasets were established using data preprocessing and standardization. Hyperparameter tuning was performed to develop the RF and GBM models. The model performances were evaluated using the leave-one-out cross-validation technique. The study demonstrated that, for small datasets comprising mainly categorical variables, the bagging technique (RF) predictions were more stable and accurate than those of the boosting technique (GBM). However, GBM models demonstrated excellent predictive performance in some DW predictive models. Furthermore, the RF and GBM predictive models demonstrated significantly differing performance across different types of DW. Certain RF and GBM models demonstrated relatively low predictive performance. However, the remaining predictive models all demonstrated excellent predictive performance at R2 values > 0.6, and R values > 0.8. Such differences are mainly because of the characteristics of features applied to model development; we expect the application of additional features to improve the performance of the predictive models. The 11 DW predictive models developed in this study will be useful for establishing detailed DW management strategies.

Nandy A., Duan C., Taylor M.G., Liu F., Steeves A.H., Kulik H.J.

Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.

Vujovic Ž.Ð.